nl8590687
|
e4104f091a
|
can not parallel and move it to trash
|
2018-04-11 16:46:46 +08:00 |
|
nl8590687
|
8175f3c8c7
|
try to parallel
|
2018-04-11 16:33:15 +08:00 |
|
nl8590687
|
c5996dc3a8
|
优化程序结构，以及减少IO次数
|
2018-04-11 15:05:01 +08:00 |
|
nl8590687
|
49de23dbae
|
add data preprocessing
|
2018-04-10 15:29:33 +08:00 |
|
nl8590687
|
cb69b5f798
|
a little change
|
2018-04-10 14:41:59 +08:00 |
|
nl8590687
|
60340059d2
|
add ctc decode function
|
2018-04-09 21:58:20 +08:00 |
|
nl8590687
|
7eeb5ade96
|
Merge branch 'master' of github.com:nl8590687/ASRT_SpeechRecognition
|
2018-04-09 17:18:25 +08:00 |
|
nl8590687
|
69c3f33101
|
modify model 5 to try
|
2018-04-09 17:17:41 +08:00 |
|
nl8590687
|
a6f563bced
|
Merge pull request #6 from ZJUGuoShuai/fix-dataset-link
Update invalid data set download link
|
2018-04-09 02:42:21 -05:00 |
|
Guo
|
6aaac30ec4
|
Update invalid data set download link
The old THCHS30 download link is invalid now and moved to a new mirror.
|
2018-04-09 09:27:25 +08:00 |
|
nl8590687
|
5b127ac63c
|
一些小修改
|
2018-04-08 22:44:14 +08:00 |
|
nl8590687
|
618835d3bf
|
修改模型2的初始化和激活函数
|
2018-04-08 17:00:34 +08:00 |
|
nl8590687
|
1425994db3
|
修改了模型5的参数初始化
|
2018-04-08 16:22:46 +08:00 |
|
nl8590687
|
8b59183c00
|
try again 20180407_1
|
2018-04-07 16:17:55 +08:00 |
|
nl8590687
|
00061ab74e
|
try 20180407_0
|
2018-04-07 14:47:40 +08:00 |
|
nl8590687
|
1398b068a3
|
bug修复以及一些尝试
|
2018-04-05 21:56:28 +08:00 |
|
nl8590687
|
8b9d086ab2
|
fix bugs
|
2018-04-05 19:08:19 +08:00 |
|
nl8590687
|
b36efdbdf0
|
修改标签输入试试20180405_1
|
2018-04-05 18:57:39 +08:00 |
|
nl8590687
|
700186a821
|
修改网络模型20180405_0
|
2018-04-05 16:45:55 +08:00 |
|
nl8590687
|
2ba53cdca5
|
修改了数据的输入
|
2018-04-04 22:16:07 +08:00 |
|
nl8590687
|
5a31fc69cc
|
修改了一下模型试试20180403
|
2018-04-03 14:28:35 +08:00 |
|
nl8590687
|
ab8aa584e5
|
更换优化器试试
|
2018-04-02 17:11:33 +08:00 |
|
nl8590687
|
555997ff3f
|
add bn layer
|
2018-04-01 21:56:46 +08:00 |
|
nl8590687
|
2fe748571d
|
fix bugs
|
2018-04-01 20:05:12 +08:00 |
|
nl8590687
|
58d02601a7
|
增加了跨平台支持
|
2018-04-01 17:16:38 +08:00 |
|
nl8590687
|
cc0572b3b7
|
修正格式
|
2018-03-30 23:06:43 +08:00 |
|
nl8590687
|
6861398f57
|
修复了一大堆bug...
|
2018-03-30 23:04:11 +08:00 |
|
nl8590687
|
7d69729035
|
一个暂时能训练的版本，可能会炸
|
2018-03-29 15:30:50 +08:00 |
|
nl8590687
|
7c59bf7874
|
似乎能训练了？
|
2018-03-28 23:10:41 +08:00 |
|
nl8590687
|
de9692e5f4
|
CTC基本实现，开始修复涉及数据的代码bug
|
2018-03-28 17:34:22 +08:00 |
|
nl8590687
|
6517062b94
|
add ctc loss and fixed bugs
|
2018-03-11 21:21:12 +08:00 |
|
nl8590687
|
2ec4b937c9
|
添加ctc层基本框架
|
2018-03-10 22:30:20 +08:00 |
|
nl8590687
|
4ca877a046
|
基本完成除添加模型之外的其他部分，不过尚未测试
|
2017-09-08 20:18:46 +08:00 |
|
nl8590687
|
c621c0aeb9
|
模型训练部分基本完成
|
2017-09-08 12:26:01 +08:00 |
|
nl8590687
|
8f753d81c5
|
add fit_generator code to be modified
|
2017-09-06 18:22:20 +08:00 |
|
nl8590687
|
5f73fe0599
|
update daily 20170904
|
2017-09-04 22:36:11 +08:00 |
|
nl8590687
|
740b65f884
|
update daily 20170831
|
2017-08-31 21:50:20 +08:00 |
|
nl8590687
|
179225cd81
|
update daily 20170829
|
2017-08-30 00:15:03 +08:00 |
|
nl8590687
|
2217754bf0
|
add read words list and signal scale
|
2017-08-29 00:06:08 +08:00 |
|
nl8590687
|
ab74ee4bfc
|
implement to read wav files and list files.
|
2017-08-26 23:40:28 +08:00 |
|
nl8590687
|
2cdeeaa9a7
|
add license and gitignore.modify py code main.py
|
2017-08-22 17:56:05 +08:00 |
|
nl8590687
|
80dbdb011b
|
add some files and codes
|
2017-03-19 21:07:31 +08:00 |
|
nl8590687
|
64011ff315
|
Merge pull request #2 from szlll/master
test -by szlll
|
2017-03-09 16:36:09 +08:00 |
|
szlll
|
8805e26aee
|
test -by szlll
|
2017-03-09 16:29:43 +08:00 |
|
nl8590687
|
d072cba26e
|
add some words for readme.md
|
2017-03-08 16:17:50 +08:00 |
|
nl8590687
|
c5d1c346ab
|
add some words for readme.md
|
2017-03-08 16:12:53 +08:00 |
|
nl8590687
|
df41a971bb
|
Merge pull request #1 from williamchenwl/master
williamchen 3/7
|
2017-03-07 20:52:09 +08:00 |
|
williamchen
|
85caf7e3b5
|
williamchen 3/7
|
2017-03-07 19:56:00 +08:00 |
|
nl8590687
|
b8ce475d1c
|
Initial commit
|
2017-03-06 23:28:22 +08:00 |